Langevin Monte Carlo: Randomized Midpoint Method Revisited
Offered By: Alan Turing Institute via YouTube
Course Description
Overview
Explore the Randomized Midpoint Langevin Monte Carlo (RMP-LCM) method in this 39-minute lecture by Arnak Dalalyan from ENSAE Paris, France. Delve into the efficiency and widespread use of Langevin Monte Carlo for generating random samples from target distributions in high-dimensional Euclidean spaces. Examine various Langevin Monte Carlo variants and understand why RMP-LCM offers the best known non-asymptotic theoretical guarantees on sampling error for target distributions with continuous Lipschitz gradient log-densities. Review existing results, discover extensions, and learn about recent improvements to this powerful sampling technique.
Syllabus
Langevin Monte Carlo Randomised mid point method revisited
Taught by
Alan Turing Institute
Related Courses
Neuronal DynamicsÉcole Polytechnique Fédérale de Lausanne via edX Neuronal Dynamics
École Polytechnique Fédérale de Lausanne via edX Risk and Reliability of offshore structures
Indian Institute of Technology Madras via Swayam Stochastic Processes
Indian Institute of Technology Delhi via Swayam Introductory Statistics : Basic Ideas and Instruments for Statistical Inference
Seoul National University via edX